Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Isolation of infectious SARS-CoV-2 from urine of a COVID-19 patient.

Emerging microbes & infections·2020
Same author

Low shear stress induces endothelial cell apoptosis and monocyte adhesion by upregulating PECAM‑1 expression.

Molecular medicine reports·2020
Same author

Real-Ambient Particulate Matter Exposure-Induced Cardiotoxicity in C57/B6 Mice.

Frontiers in pharmacology·2020
Same author

The Role of Frontal and Occipital Cortices in Processing Sustained Visual Attention in Young Adults with Attention-Deficit/Hyperactivity Disorder: A Functional Near-Infrared Spectroscopy Study.

Neuroscience bulletin·2020
Same author

Gut microbiota and Chinese medicine syndrome: altered fecal microbiotas in spleen (Pi)-deficient patients.

Journal of traditional Chinese medicine = Chung i tsa chih ying wen pan·2020
Same author

Correlation between lower extremity arterial disease and skeletal muscle mass in patients with type 2 diabetes mellitus.

The Journal of international medical research·2020

Related Experiment Video

Updated: Jul 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

An improved supervised and attention mechanism-based U-Net algorithm for retinal vessel segmentation.

Zhendi Ma1, Xiaobo Li1

  • 1School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China.

Computers in Biology and Medicine
|December 6, 2023
PubMed
Summary
This summary is machine-generated.

This study enhances retinal blood vessel segmentation for diagnosing eye diseases using a novel U-Net algorithm with attention mechanisms. The improved method accurately detects small vessels and edges, boosting diagnostic capabilities.

Keywords:
Attention mechanismRetinal vessel segmentationSqueeze-and-excitationSupervised fusion moduleU-net

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

406

Related Experiment Videos

Last Updated: Jul 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

406

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • Accurate retinal blood vessel segmentation is vital for diagnosing various systemic and ocular diseases.
  • Existing methods struggle with segmenting fine vessels and precise edge details.

Purpose of the Study:

  • To develop an advanced U-Net algorithm for improved retinal blood vessel segmentation.
  • To enhance the detection of small vessels and vessel edges for better diagnostic accuracy.

Main Methods:

  • Introduced a supervised attention mechanism within the U-Net architecture.
  • Implemented a decoder fusion module (DFM) for comprehensive feature extraction.
  • Proposed a context squeeze and excitation (CSE) decoding module for enhanced feature representation.
  • Utilized a supervised fusion mechanism (SFM) for multi-scale feature integration.

Main Results:

  • The proposed network demonstrated excellent performance on public datasets (DRIVE, STARE, CHASED_B1).
  • Significant improvements were observed in segmenting small vessels and vessel edges.
  • The integration of multi-scale features enhanced overall segmentation accuracy.

Conclusions:

  • The novel U-Net with supervised attention mechanism offers superior retinal blood vessel segmentation.
  • This approach holds promise for improving automated diagnosis of ophthalmic and systemic diseases.
  • The method effectively integrates low-level and high-level features for robust performance.